Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4714 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.9666. Min Range: -3.9666

Max Act: 3.9666. Min Act: -0.0000

Data Index: 864994 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 3.9666. Min Range: -3.9666

Max Act: 2.8790. Min Act: -0.0000

Data Index: 1205203 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 3.9666. Min Range: -3.9666

Max Act: 3.1793. Min Act: -0.0000

Data Index: 202121 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 3.9666. Min Range: -3.9666

Max Act: 2.5735. Min Act: -0.0000

Data Index: 491540 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 3.9666. Min Range: -3.9666

Max Act: 2.7230. Min Act: -0.0000

Data Index: 46757 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 3.9666. Min Range: -3.9666

Max Act: 2.6781. Min Act: -0.0000

Data Index: 534295 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 3.9666. Min Range: -3.9666

Max Act: 2.5644. Min Act: -0.0000

Data Index: 617210 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 3.9666. Min Range: -3.9666

Max Act: 2.4053. Min Act: -0.0000

Data Index: 729147 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 3.9666. Min Range: -3.9666

Max Act: 2.4037. Min Act: -0.0000

Data Index: 974134 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 3.9666. Min Range: -3.9666

Max Act: 2.5238. Min Act: -0.0000

Data Index: 978408 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 3.9666. Min Range: -3.9666

Max Act: 2.3854. Min Act: -0.0000

Data Index: 735531 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 3.9666. Min Range: -3.9666

Max Act: 2.4974. Min Act: -0.0000

Data Index: 639322 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 3.9666. Min Range: -3.9666

Max Act: 2.4456. Min Act: -0.0000

Data Index: 376505 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 3.9666. Min Range: -3.9666

Max Act: 2.4409. Min Act: -0.0000

Data Index: 938449 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 3.9666. Min Range: -3.9666

Max Act: 2.5746. Min Act: -0.0000

Data Index: 341273 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 3.9666. Min Range: -3.9666

Max Act: 2.6238. Min Act: -0.0000

Data Index: 1037894 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 3.9666. Min Range: -3.9666

Max Act: 2.3545. Min Act: -0.0000

Data Index: 550914 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 3.9666. Min Range: -3.9666

Max Act: 2.4462. Min Act: -0.0000

Data Index: 51403 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 3.9666. Min Range: -3.9666

Max Act: 2.2856. Min Act: -0.0000

Data Index: 331871 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 3.9666. Min Range: -3.9666

Max Act: 2.1103. Min Act: -0.0000

Data Index: 1073878 (C4 (Web Text))

Max Activating Token Index: 383